{"id":16729,"date":"2022-03-23T10:54:53","date_gmt":"2022-03-23T10:54:53","guid":{"rendered":"https:\/\/clinlabint.com\/?p=16729"},"modified":"2022-03-23T10:54:53","modified_gmt":"2022-03-23T10:54:53","slug":"fingerprint-machine-learning-technique-identifies-different-bacteria-in-seconds","status":"publish","type":"post","link":"https:\/\/clinlabint.com\/fingerprint-machine-learning-technique-identifies-different-bacteria-in-seconds\/","title":{"rendered":"‘Fingerprint’ machine learning technique identifies different bacteria in seconds"},"content":{"rendered":"
\n

\r\n\"Bio-Rad<\/a>\r\n<\/p>\n<\/div><\/section><\/div>

<\/p>\n<\/div><\/section>
\n

‘Fingerprint’ machine learning technique identifies different bacteria in seconds<\/h1>\/ in E-News<\/a> <\/span><\/span><\/header>\n<\/div><\/section>
\n

Bacterial identification can take hours and often longer, precious time when diagnosing infections and selecting appropriate treatments. There may be a quicker, more accurate process according to researchers at KAIST (Korea Advanced Institute of Science and Technology). By teaching a deep learning algorithm to identify the \u201cfingerprint\u201d spectra of the molecular components of various bacteria, the researchers could classify various bacteria in different media with accuracies of up to 98%.<\/p>\n

<\/p>\n

Their results were made available online on January 18 in Biosensors and Bioelectronics, ahead of publication in the journal\u2019s April issue.<\/p>\n

Bacteria-induced illnesses, those caused by direct bacterial infection or by exposure to bacterial toxins, can induce painful symptoms and even lead to death, so the rapid detection of bacteria is crucial to prevent the intake of contaminated foods and to diagnose infections from clinical samples, such as urine.<\/p>\n

\u201cBy using surface-enhanced Raman spectroscopy (SERS) analysis boosted with a newly proposed deep learning model, we demonstrated a markedly simple, fast, and effective route to classify the signals of two common bacteria and their resident media without any separation procedures,\u201d said Professor Sungho Jo from the School of Computing.<\/p>\n

Raman spectroscopy sends light through a sample to see how it scatters. The results reveal structural information about the sample \u2014 the spectral fingerprint \u2014 allowing researchers to identify its molecules. The surface-enhanced version places sample cells on noble metal nanostructures that help amplify the sample\u2019s signals.<\/p>\n

However, it is challenging to obtain consistent and clear spectra of bacteria due to numerous overlapping peak sources, such as proteins in cell walls. \u201cMoreover, strong signals of surrounding media are also enhanced to overwhelm target signals, requiring time-consuming and tedious bacterial separation steps,\u201d said Professor Yeon Sik Jung from the Department of Materials Science and Engineering.<\/p>\n

To parse through the noisy signals, the researchers implemented an artificial intelligence method called deep learning that can hierarchically extract certain features of the spectral information to classify data. They specifically designed their model, named the dual-branch wide-kernel network (DualWKNet), to efficiently learn the correlation between spectral features. Such an ability is critical for analysing one-dimensional spectral data, according to Professor Jo.<\/p>\n

\u201cDespite having interfering signals or noise from the media, which make the general shapes of different bacterial spectra and their residing media signals look similar, high classification accuracies of bacterial types and their media were achieved,\u201d Professor Jo said, explaining<\/p>\n

that DualWKNet allowed the team to identify key peaks in each class that were almost indiscernible in individual spectra, enhancing the classification accuracies. \u201cUltimately, with the use of DualWKNet replacing the bacteria and media separation steps, our method dramatically reduces analysis time.\u201d<\/p>\n

The researchers plan to use their platform to study more bacteria and media types, using the information to build a training data library of various bacterial types in additional media to reduce the collection and detection times for new samples.<\/p>\n

\u201cWe developed a meaningful universal platform for rapid bacterial detection with the collaboration between SERS and deep learning,\u201d Professor Jo said. \u201cWe hope to extend the use of our deep learning-based SERS analysis platform to detect numerous types of bacteria in additional media that are important for food or clinical analysis, such as blood.\u201d<\/p>\n<\/div><\/section>
\n

\"\"<\/div><\/div><\/div>
\n

Schematics of the general process of Raman data collection and analysis where a single spectrum is attained from a single cell and classified via deep learning.<\/b><\/em><\/p>\n<\/div><\/section>
\n